Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ウィ
    -0.07
    ��
    -0.06
    usp
    -0.06
    าว
    -0.06
    �州
    -0.06
    eut
    -0.06
    785
    -0.06
    itone
    -0.06
    lements
    -0.06
     yêu
    -0.06
    POSITIVE LOGITS
    success
    0.09
    _success
    0.07
     longing
    0.07
     формы
    0.07
     fleece
    0.06
     DirectoryInfo
    0.06
     �
    0.06
     إذا
    0.06
     ended
    0.06
     worth
    0.06
    Act Density 0.005%

    No Known Activations